save_chat_excerpt

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It does so reasonably well by revealing that the LLM auto-titles the page when no suggested_title is provided and that a created_via: mcp marker is added for audit. It does not dwell on failure modes or permission effects, but the most relevant behavior is exposed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact, front-loads the central write action, and adds two substantive behaviors in a second short sentence. Nothing feels wasted, though additional structured routing or an explicit alternative could make it slightly more useful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 3-parameter create-style tool with no output schema, this description covers the main purpose, the auto-title edge case, and the audit stamp. It does not explain return/confirmation behavior or the exact semantics of source_chat_id, but the agent can still invoke the tool correctly in the common content-only case.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, so the tool description must compensate. It gives meaning to content via 'fragment of the current AI conversation' and explains the fallback when suggested_title is absent. However, source_chat_id is never explicitly described, leaving one of three parameters only inferable from its name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete action and resource: saving a fragment of the current AI conversation as a wiki page. It also adds distinguishing behaviors such as auto-titling and the created_via audit marker. It does not explicitly contrast itself with sibling creation tools like create_note or quick_capture, so it is clear but not fully differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context: you use this when you want to preserve a fragment of the current AI conversation in the wiki. It does not state when to prefer this over alternatives, nor does it give exclusions or conditions for choosing a sibling tool among the many creation/capture tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.